Data Processing Method and System Based on Smart Park Cloud Collaboration System

Abstract

An embodiment of the present invention provides a data processing method and system based on a smart park cloud collaboration system. First, a first cloud collaboration function anomaly observation network that has completed knowledge learning analyzes the monitoring data and generates system operation anomaly category observation data. If these anomaly observation data meet the accuracy requirements, they are output as initial anomaly category observation data and used as sample data for knowledge learning by the second cloud collaboration function anomaly observation network. If the anomaly observation data do not meet the accuracy requirements, the initial anomaly category observation data generated by prior knowledge annotation is obtained and output together with the original monitoring data as sample data for knowledge learning by the second cloud collaboration function anomaly observation network. This method can improve the accuracy and efficiency of anomaly detection and provide reliable sample data for subsequent knowledge learning.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular, to a data processing method and system based on a cloud collaboration system for an intelligent park. Background Art

[0002] The cloud collaboration system of an intelligent park is a system that uses cloud computing and collaboration technologies to enable multi-user collaborative work, and can promote collaboration and information exchange among multiple intelligent park users by sharing resources, data, and application programs.

[0003] However, in the existing cloud collaboration system, due to large-scale data and complex system operations, monitoring and anomaly analysis of the cloud collaboration system are a challenge. How to accurately detect and identify abnormal situations in the system operation and perform effective analysis and processing remains a problem. Moreover, a high accuracy requirement is imposed on the abnormal observation data to ensure that the generated data can accurately reflect the abnormal categories in the system operation. However, the existing technologies often fail to meet this requirement, resulting in unsatisfactory quality and reliability of the abnormal data. Summary of the Invention

[0004] In view of this, the purpose of the embodiments of the present invention is to provide a data processing method and system based on a cloud collaboration system for an intelligent park. First, through the first cloud collaboration function abnormal observation network that has completed knowledge learning, the monitoring data is analyzed to generate abnormal category observation data for the system operation. If these abnormal observation data meet the accuracy requirements, they are output as initial abnormal category observation data and used as sample data for knowledge learning by the second cloud collaboration function abnormal observation network. If the abnormal observation data does not meet the accuracy requirements, the initial abnormal category observation data generated by prior knowledge annotation is obtained and output together with the original monitoring data as sample data for knowledge learning by the second cloud collaboration function abnormal observation network. This method can improve the accuracy and efficiency of anomaly detection and provide reliable sample data for subsequent knowledge learning.

[0005] According to one aspect of the embodiments of the present invention, there is provided a data processing method and system based on a cloud collaboration system for an intelligent park, and the method includes:

[0006] Performing anomaly analysis on the monitoring data of the first template cloud collaboration system according to the first cloud collaboration function abnormal observation network that has completed knowledge learning, and generating first system operation abnormal category observation data corresponding to the monitoring data of the first template cloud collaboration system;

[0007] If the first system operation abnormality category observation data meets the accuracy requirement, the first system operation abnormality category observation data is output as the initial abnormality category observation data corresponding to the first template cloud collaborative system monitoring data, and the first template cloud collaborative system monitoring data and the corresponding initial abnormality category observation data are output as sample learning data of the second cloud collaborative function abnormality observation network waiting for knowledge learning;

[0008] If the abnormality category observation data of the first system operation does not meet the accuracy requirements, the initial abnormality category observation data generated by prior knowledge annotation of the first template cloud collaborative system monitoring data is obtained, and the first template cloud collaborative system monitoring data and the initial abnormality category observation data generated by prior knowledge annotation are output as sample learning data of the second cloud collaborative function abnormality observation network waiting for knowledge learning.

[0009] In an alternative embodiment, the first system operation abnormality category observation data includes observed abnormality category information, and the initial abnormality category observation data includes initial abnormality category information.

[0010] In an alternative embodiment, the observed anomaly category information includes probability values corresponding to a plurality of candidate anomaly categories, and the accuracy requirement includes a target probability value in the observed anomaly category information that is greater than a set probability value.

[0011] In an alternative embodiment, the method further comprises:

[0012] Obtain any template cloud collaborative system monitoring data and corresponding initial abnormality category observation data from the sample learning data of the second cloud collaborative function abnormality observation network waiting for knowledge learning;

[0013] The monitoring data of any one of the template cloud collaborative system is updated to expand the depth of abnormality analysis, and the monitoring data of the second template cloud collaborative system is generated. According to the initial abnormality category observation data corresponding to the monitoring data of any one of the template cloud collaborative system, the initial abnormality category observation data corresponding to the monitoring data of the second template cloud collaborative system is determined, and the second template cloud collaborative system monitoring data and the corresponding initial abnormality category observation data are output as sample learning data of the second cloud collaborative function abnormality observation network waiting for knowledge learning.

[0014] In an alternative embodiment, before obtaining any template cloud collaborative system monitoring data and corresponding initial abnormality category observation data from the sample learning data of the second cloud collaborative function abnormality observation network waiting for knowledge learning, the method further includes:

[0015] Obtain the cloud collaboration knowledge vector sequence of the template cloud collaboration system monitoring data corresponding to the abnormal system operation category observation data in the sample learning data that does not meet the accuracy requirements;

[0016] Determine the collaboration function crash label corresponding to each cloud collaboration knowledge vector sequence, and determine the target collaboration function crash label whose proportion of the number of cloud collaboration knowledge vector sequences it contains in all cloud collaboration knowledge vector sequences is greater than the set proportion;

[0017] According to the corresponding relationship between the collaboration function crash label and the expansion strategy for expanding the depth of anomaly analysis, determine the target expansion strategy corresponding to the target collaboration function crash label;

[0018] The update for expanding the depth of anomaly analysis of any template cloud collaboration system monitoring data to generate the second template cloud collaboration system monitoring data includes:

[0019] Update any template cloud collaboration system monitoring data according to the target expansion strategy to generate the second template cloud collaboration system monitoring data.

[0020] In an alternative implementation, the first template cloud collaboration system monitoring data is a cloud collaboration status operation monitoring segment of the reference cloud collaboration status operation monitoring flow;

[0021] The method further includes:

[0022] Perform knowledge learning on the second cloud collaboration function anomaly observation network waiting for knowledge learning according to the sample learning data;

[0023] Input the cloud collaboration status operation monitoring segment of the reference cloud collaboration status operation monitoring flow into the second cloud collaboration function anomaly observation network that has completed knowledge learning to generate the second system operation abnormal category observation data.

[0024] According to another aspect of the embodiments of the present invention, there is provided a data processing method and system for a smart park cloud collaboration system, and the system includes:

[0025] A generation unit, configured to perform anomaly analysis on the first template cloud collaboration system monitoring data according to the first cloud collaboration function anomaly observation network that has completed knowledge learning, and generate the first system operation abnormal category observation data corresponding to the first template cloud collaboration system monitoring data;

[0026] The first output unit is configured to, if the observation data of the abnormal operation category of the first system meets the accuracy requirement, output the observation data of the abnormal operation category of the first system as the initial abnormal operation category observation data corresponding to the monitoring data of the first template cloud collaboration system, and output the monitoring data of the first template cloud collaboration system and the corresponding initial abnormal operation category observation data as the sample learning data of the second cloud collaboration function abnormal observation network waiting for knowledge learning;

[0027] The second output unit is configured to, if the observation data of the abnormal operation category of the first system does not meet the accuracy requirement, obtain the initial abnormal operation category observation data generated by performing prior knowledge annotation on the monitoring data of the first template cloud collaboration system, and output the monitoring data of the first template cloud collaboration system and the initial abnormal operation category observation data generated by performing prior knowledge annotation as the sample learning data of the second cloud collaboration function abnormal observation network waiting for knowledge learning.

[0028] According to another aspect of the embodiments of the present invention, there is provided a computer device, which includes a processor and a memory. At least one instruction is stored in the memory, and the at least one instruction is loaded and executed by the processor to implement the operations performed by the data processing method based on the intelligent park cloud collaboration system as described in any one of the above.

[0029] According to another aspect of the embodiments of the present invention, there is provided a computer-readable storage medium, in which at least one instruction is stored, and the at least one instruction is loaded and executed by a processor to implement the operations performed by the data processing method based on the intelligent park cloud collaboration system as described in any one of the above.

[0030] To make the above objects, features, and advantages of the embodiments of the present invention more obvious and understandable, the following will be described in detail in conjunction with the embodiments and the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] To more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required in the embodiments. It should be understood that the following drawings only show some embodiments of the present invention, and thus should not be regarded as limiting the scope. For those of ordinary skill in the art, other related drawings can be obtained based on these drawings without creative efforts.

[0032] Figure 1 Shows a schematic diagram of the components of the server provided by the embodiments of the present invention;

[0033] Figure 2 Shows a schematic flowchart of the data processing method based on the intelligent park cloud collaboration system provided by the embodiments of the present invention;

[0034] Figure 3 The functional module block diagram of the data processing system based on the intelligent park cloud collaboration system provided by the embodiments of the present invention is shown. Detailed implementation manners

[0035] In order to enable the trainees in the technical field to better understand the solution of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the scope of protection of the present invention.

[0036] The terms "first", "second", "third", etc. (if any) in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that such used data may be interchanged under appropriate circumstances so that the embodiments of the present invention described herein can be implemented in an order different from those illustrated or described herein. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device that includes a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0037] Figure 1 The exemplary component schematic diagram of the server 100 is shown. The server 100 may include one or more processors 104, such as one or more central processing units (CPUs), and each processing unit may implement one or more hardware threads. The server 100 may also include any storage medium 106 for storing any kind of information such as code, settings, data, etc. Non-limitingly, for example, the storage medium 106 may include any one or more combinations of the following: any type of RAM, any type of ROM, flash memory devices, hard disks, optical discs, etc. More generally, any storage medium may use any technology to store information. Further, any storage medium may provide volatile or non-volatile retention of information. Further, any storage medium may represent a fixed or removable component of the server 100. In one case, when the processor 104 executes the associated instructions stored in any storage medium or combination of storage media, the server 100 may perform any operation of the associated instructions. The server 100 also includes one or more drive units 108 for interacting with any storage medium, such as a hard disk drive unit, an optical disc drive unit, etc.

[0038] Server 100 also includes Input / Output 110 (I / O) which is used to receive various inputs (via input unit 112) and to provide various outputs (via output unit 114). A specific output mechanism may include a presentation device 116 and an associated Graphical User Interface (GUI) 118. Server 100 may also include one or more network interfaces 120 which are used to exchange data with other devices via one or more communication units 122. One or more communication buses 124 couple the components described above together.

[0039] Communication unit 122 may be implemented in any manner, for example, via a local area network, a wide area network (e.g., the Internet), a point-to-point connection, etc., or any combination thereof. Communication unit 122 may include any combination of hardwired links, wireless links, routers, gateway functions, name servers 100, etc. governed by any protocol or combination of protocols.

[0040] Figure 2 A schematic flowchart of a data processing method and system based on a smart park cloud collaboration system provided by an embodiment of the present invention is shown. The data processing method and system based on the smart park cloud collaboration system may be executed by Figure 1 the server 100 shown in the figure, and the detailed steps of the data processing method based on the smart park cloud collaboration system are introduced as follows.

[0041] Step S110: Based on the first cloud collaboration function anomaly observation network that has completed knowledge learning, perform anomaly analysis on the monitoring data of the first template cloud collaboration system to generate first system operation anomaly category observation data corresponding to the monitoring data of the first template cloud collaboration system;

[0042] Step S120: If the first system operation anomaly category observation data meets the accuracy requirements, output the first system operation anomaly category observation data as initial anomaly category observation data corresponding to the monitoring data of the first template cloud collaboration system, and output the monitoring data of the first template cloud collaboration system and the corresponding initial anomaly category observation data as sample learning data for the second cloud collaboration function anomaly observation network waiting for knowledge learning;

[0043] Step S130: If the first system operation anomaly category observation data does not meet the accuracy requirements, obtain the initial anomaly category observation data generated by performing prior knowledge annotation on the monitoring data of the first template cloud collaboration system, and output the monitoring data of the first template cloud collaboration system and the initial anomaly category observation data generated by performing prior knowledge annotation as sample learning data for the second cloud collaboration function anomaly observation network waiting for knowledge learning.

[0044] Based on the above steps, in this embodiment, first, through the first cloud collaboration function anomaly observation network that has completed knowledge learning, the monitoring data is analyzed to generate system operation anomaly category observation data. If these anomaly observation data meet the accuracy requirements, they are output as initial anomaly category observation data and used as sample data for knowledge learning by the second cloud collaboration function anomaly observation network. If the anomaly observation data does not meet the accuracy requirements, the initial anomaly category observation data generated by prior knowledge annotation is obtained, and it is output together with the original monitoring data as sample data for knowledge learning by the second cloud collaboration function anomaly observation network. This method can improve the accuracy and efficiency of anomaly detection and provide reliable sample data for subsequent knowledge learning.

[0045] In an alternative implementation, the first system operation anomaly category observation data includes observation anomaly category information, and the initial anomaly category observation data includes initial anomaly category information.

[0046] In an alternative implementation, the observation anomaly category information includes probability values corresponding to multiple candidate anomaly categories, and the accuracy requirements include that the observation anomaly category information has a target probability value greater than the set probability value.

[0047] In an alternative implementation, the method further includes:

[0048] In the sample learning data of the second cloud collaboration function anomaly observation network waiting for knowledge learning, any template cloud collaboration system monitoring data and the corresponding initial anomaly category observation data are obtained;

[0049] The obtained any template cloud collaboration system monitoring data is updated for expanding the depth of anomaly analysis to generate second template cloud collaboration system monitoring data. According to the initial anomaly category observation data corresponding to the any template cloud collaboration system monitoring data, the initial anomaly category observation data corresponding to the second template cloud collaboration system monitoring data is determined, and the second template cloud collaboration system monitoring data and the corresponding initial anomaly category observation data are output as the sample learning data of the second cloud collaboration function anomaly observation network waiting for knowledge learning.

[0050] In an alternative implementation, before obtaining any template cloud collaboration system monitoring data and the corresponding initial anomaly category observation data in the sample learning data of the second cloud collaboration function anomaly observation network waiting for knowledge learning, the method further includes:

[0051] Obtain the cloud collaboration knowledge vector sequence of the template cloud collaboration system monitoring data whose corresponding system operation anomaly category observation data in the sample learning data does not meet the accuracy requirements;

[0052] Determine the collaborative function crash label corresponding to each cloud collaborative knowledge vector sequence, and determine the target collaborative function crash label whose proportion of the number of cloud collaborative knowledge vector sequences it contains in all cloud collaborative knowledge vector sequences is greater than the set proportion;

[0053] According to the corresponding relationship between the collaborative function crash label and the expansion strategy for expanding the depth of anomaly analysis, determine the target expansion strategy corresponding to the target collaborative function crash label;

[0054] The updating for expanding the depth of anomaly analysis of the monitoring data of any template cloud collaborative system to generate the monitoring data of the second template cloud collaborative system includes:

[0055] Update the monitoring data of any template cloud collaborative system according to the target expansion strategy to generate the monitoring data of the second template cloud collaborative system.

[0056] In an alternative embodiment, the monitoring data of the first template cloud collaborative system is a cloud collaborative status operation monitoring segment referring to the cloud collaborative status operation monitoring flow;

[0057] The method further includes:

[0058] Perform knowledge learning on the second cloud collaborative function anomaly observation network waiting for knowledge learning according to the sample learning data;

[0059] Input the cloud collaborative status operation monitoring segment of the reference cloud collaborative status operation monitoring flow into the second cloud collaborative function anomaly observation network that has completed knowledge learning to generate the second system operation anomaly category observation data.

[0060] Figure 3 FIG. shows a functional module diagram of a data processing system 200 based on a smart park cloud collaborative system provided by an embodiment of the present invention. The functions implemented by the data processing system 200 based on the smart park cloud collaborative system can correspond to the steps executed by the above method. The data processing system 200 based on the smart park cloud collaborative system can be understood as the above server 100, or the processor of the server 100, or can also be understood as a component independent of the above server 100 or processor and realizing the functions of the present invention under the control of the server 1, such as Figure 3 As shown, the functions of each functional module of the data processing system 200 based on the smart park cloud collaborative system will be elaborated in detail below.

[0061] The generating unit 210 is configured to perform anomaly analysis on the monitoring data of the first template cloud collaborative system according to the first cloud collaborative function anomaly observation network that has completed knowledge learning, and generate the first system operation anomaly category observation data corresponding to the monitoring data of the first template cloud collaborative system;

[0062] The first output unit 220 is configured to, if the first system operation anomaly category observation data meets the accuracy requirement, output the first system operation anomaly category observation data as the initial anomaly category observation data corresponding to the first template cloud collaboration system monitoring data, and output the first template cloud collaboration system monitoring data and the corresponding initial anomaly category observation data as the sample learning data of the second cloud collaboration function anomaly observation network waiting for knowledge learning;

[0063] The second output unit 230 is configured to, if the first system operation anomaly category observation data does not meet the accuracy requirement, obtain the initial anomaly category observation data generated by performing prior knowledge annotation on the first template cloud collaboration system monitoring data, and output the first template cloud collaboration system monitoring data and the initial anomaly category observation data generated by performing prior knowledge annotation as the sample learning data of the second cloud collaboration function anomaly observation network waiting for knowledge learning.

[0064] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the foregoing method embodiments, and will not be described herein again.

[0065] For those skilled in the art, it is obvious that the present invention is not limited to the details of the above exemplary embodiments, and can be implemented in other specific forms without departing from the spirit or basic characteristics of the present invention. Therefore, from any point of view, the embodiments should be regarded as exemplary and non-limiting. The scope of the present invention is defined by the appended claims rather than the above description. Therefore, it is intended to embrace all changes falling within the meaning and scope of the equivalent elements of the claims in the present invention.

Claims

1. A data processing method based on a smart park cloud collaboration system, characterized in that, The method includes: Performing anomaly analysis on the monitoring data of the first template cloud collaboration system according to the first cloud collaboration function anomaly observation network that has completed knowledge learning, to generate first system operation anomaly category observation data corresponding to the monitoring data of the first template cloud collaboration system; the first system operation anomaly category observation data includes observation anomaly category information, and the observation anomaly category information includes probability values corresponding to multiple candidate anomaly categories. The accuracy requirement is that the observation anomaly category information has a target probability value greater than the set probability value; the monitoring data of the first template cloud collaboration system is a cloud collaboration status operation monitoring segment of the reference cloud collaboration status operation monitoring flow; If the first system operation anomaly category observation data meets the accuracy requirement, then output the first system operation anomaly category observation data as the initial anomaly category observation data corresponding to the monitoring data of the first template cloud collaboration system. The initial anomaly category observation data includes initial anomaly category information, and output the monitoring data of the first template cloud collaboration system and the corresponding initial anomaly category observation data as the sample learning data of the second cloud collaboration function anomaly observation network waiting for knowledge learning; If the first system operation anomaly category observation data does not meet the accuracy requirement, then obtain the initial anomaly category observation data generated by performing prior knowledge annotation on the monitoring data of the first template cloud collaboration system, and output the monitoring data of the first template cloud collaboration system and the initial anomaly category observation data generated by performing prior knowledge annotation as the sample learning data of the second cloud collaboration function anomaly observation network waiting for knowledge learning; Obtain the cloud collaboration knowledge vector sequence of the template cloud collaboration system monitoring data whose corresponding system operation anomaly category observation data in the sample learning data does not meet the accuracy requirement; Determine the collaboration function crash label corresponding to each cloud collaboration knowledge vector sequence, and determine the target collaboration function crash label whose proportion of the number of cloud collaboration knowledge vector sequences it contains in all cloud collaboration knowledge vector sequences is greater than the set proportion; According to the corresponding relationship between the collaboration function crash label and the extension strategy for expanding the depth of anomaly analysis, determine the target extension strategy corresponding to the target collaboration function crash label; In the sample learning data, obtain any monitoring data of the template cloud collaboration system and the corresponding initial anomaly category observation data; according to the target extension strategy, perform an update for expanding the depth of anomaly analysis on any monitoring data of the template cloud collaboration system to generate the monitoring data of the second template cloud collaboration system. According to the initial anomaly category observation data corresponding to any monitoring data of the template cloud collaboration system, determine the initial anomaly category observation data corresponding to the monitoring data of the second template cloud collaboration system, and output the monitoring data of the second template cloud collaboration system and the corresponding initial anomaly category observation data as the sample learning data; Perform knowledge learning on the second cloud collaboration function anomaly observation network according to the sample learning data; Input the cloud collaboration status operation monitoring segment of the reference cloud collaboration status operation monitoring flow into the second cloud collaboration function anomaly observation network that has completed knowledge learning to generate second system operation anomaly category observation data.

2. A computer device, characterized in that, The computer device includes a processor and a memory, and at least one instruction is stored in the memory. The at least one instruction is loaded and executed by the processor to implement the operations performed by the data processing method based on the intelligent park cloud collaboration system as described in claim 1.

3. A computer-readable storage medium, characterized in that, At least one instruction is stored in the storage medium. The at least one instruction is loaded and executed by the processor to implement the operations performed by the data processing method based on the intelligent park cloud collaboration system as described in claim 1.

Images